← Back to all news
arXiv AI By Jungseob Lee, Seongtae Hong, Dongyub Jude Lee, Chanjun Park, Jaehyung Seo, Sugyeong Eo, Heuiseok Lim

Vision Is Not Overhead: One-Pass Block Drafting for Lossless Speculative Decoding in Vision-Language Models

Read the original on arXiv AI →

The paper introduces GLANCE, a one‑pass block drafting method that enables lossless speculative decoding for vision‑language models. By using a block‑diffusion head that reads the fused vision‑language state, GLANCE eliminates the need for the drafter to process the image at every step, allowing it to fill an entire block in a single forward pass. Experiments show that GLANCE can decode up to 2.93× faster than autoregressive decoding while maintaining exact greedy decoding results across multiple tasks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
4d ago

Long-Context Drafting Does Not Require Long-Context Drafters

The paper shows that long‑context drafting can be performed with short‑context drafters that are frozen and run beyond their training length, using two inference‑time mechanisms to keep their cost bounded. By bounding the attention cache and re‑basing rotary position indices, the authors demonstrate that the speedup achieved with a short‑context drafter persists up to two million tokens across multiple target‑drafter pairs and corpora. They prove that when a common index shift leaves the drafter’s computation unchanged, the acceptance gap can be tightly bounded, ensuring consistent performance.

By Aref Jafari, Vansh Bhatia, Matt Qin, Subhajit Dutta Chowdhury, Ben Lee, Vikram Appia, Ali Ghodsi, Mehdi Rezagholizadeh
fine-tuning
More like this →
arXiv AI
Aug 6

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling

arXiv:2608. 01207v2 Announce Type: replace-cross Abstract: Test-time scaling lifts large language model reasoning by sampling many candidate solutions and selecting among them, yet the same recipe transfers poorly to vision-language models (VLMs): recent work shows that simple majority voting beats selection methods built on the model's own self-verification, apparently because at the selection layer an image-grounded answer and a confident guess from the language prior look the same.

By Puzhuo Zheng, Hasan Kurban
llmsmultimodalbenchmarks
More like this →